cap-table
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted data such as shareholder names, investment amounts, and term sheet conditions to generate capitalization models. This creates a surface for indirect prompt injection.\n
- Ingestion points: User-provided inputs for dilution scenarios, SAFE conversions, and option pool calculations in SKILL.md.\n
- Boundary markers: The instructions lack explicit delimiting or instructions to the model to ignore potential commands embedded within the data it is processing.\n
- Capability inventory: No sensitive file access, network operations, or shell execution capabilities were identified.\n
- Sanitization: No data sanitization or validation logic is present to filter out malicious instructions in the input fields.
Audit Metadata